© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109495
    Prev
    Next
    INDEX
    Explanations

    configuration properties and data fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneof
    -1.08
     espera
    -0.90
    providedIn
    -0.90
     škoda
    -0.87
    わけで
    -0.84
     srebr
    -0.83
    któ
    -0.83
    呜
    -0.80
    ︠
    -0.77
    nias
    -0.77
    POSITIVE LOGITS
     reen
    1.04
    zielle
    0.95
     توضی
    0.89
     همچنین
    0.89
     มาก
    0.88
     stint
    0.88
     niña
    0.87
    などが
    0.86
     sản
    0.85
     мероприятия
    0.85
    Activations Density 0.418%

    No Known Activations